PulseAugur
EN
LIVE 22:19:33

HadamardNet improves AI model robustness against adversarial attacks

By PulseAugur Editorial · [2 sources] ·

Researchers have developed a new framework called HadamardNet to improve the robustness of object detection and semantic segmentation models against adversarial attacks. This framework utilizes Hadamard-coded output representations, which offer better calibration and allow for more effective detection of disturbances compared to traditional one-hot encodings. The novel approach includes an optimized decoding procedure and a method to exploit prediction inconsistencies for enhanced security. Evaluations show HadamardNet achieves state-of-the-art performance in detecting perturbations while maintaining competitive accuracy on clean data. AI

IMPACT Enhances AI model security by providing better detection of adversarial attacks and disturbances.

RANK_REASON The cluster contains a research paper detailing a new method for improving AI model security.

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

COVERAGE [2]

  1. arXiv cs.CV TIER_1 English(EN) · Lucas G\"ornhardt, Timo Bartels, Niklas Schwarz, Tim Fingscheidt ·

    Adversarial Attack and Disturbance Detection by Hadamard-Coded Output Representations for Object Detection and Semantic Segmentation

    arXiv:2606.09536v1 Announce Type: new Abstract: Conventional one-hot encodings often yield poorly calibrated models, being overconfident under attack, and letting entropy-based detection algorithms fail. Previous image classification works have demonstrated that Hadamard-coded ou…

  2. arXiv cs.CV TIER_1 English(EN) · Tim Fingscheidt ·

    Adversarial Attack and Disturbance Detection by Hadamard-Coded Output Representations for Object Detection and Semantic Segmentation

    Conventional one-hot encodings often yield poorly calibrated models, being overconfident under attack, and letting entropy-based detection algorithms fail. Previous image classification works have demonstrated that Hadamard-coded output representations can improve adversarial rob…

RELATED ENTITIES

RELATED TOPICS